Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    instances of punctuation or formatting indicators

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ละ
    -0.08
    anden
    -0.08
    /pg
    -0.07
    âĨ
    -0.07
    ë°į
    -0.07
    .Reporting
    -0.07
    .glide
    -0.07
    važ
    -0.07
    ocos
    -0.07
    ÑĢаг
    -0.07
    POSITIVE LOGITS
    096
    0.06
    017
    0.06
     '&#
    0.06
     otherwise
    0.06
    aka
    0.06
    ug
    0.06
     COVID
    0.05
    jak
    0.05
    ena
    0.05
    asto
    0.05
    Act Density 0.003%

    No Known Activations